Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3737 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0460. Min Range: -5.0460
Max Act: 5.0460. Min Act: -0.1700
Data Index: 5315036 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.9522. Min Act: -0.1700
Data Index: 1282358 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.9210. Min Act: -0.1700
Data Index: 6237762 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.8897. Min Act: -0.1700
Data Index: 6758822 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.8585. Min Act: -0.1700
Data Index: 3781563 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.8897. Min Act: -0.1700
Data Index: 5704903 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.8272. Min Act: -0.1700
Data Index: 3172082 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.8585. Min Act: -0.1700
Data Index: 6128919 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.8272. Min Act: -0.1700
Data Index: 6855130 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.8272. Min Act: -0.1700
Data Index: 7012210 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.8272. Min Act: -0.1700
Data Index: 5566862 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.7960. Min Act: -0.1700
Data Index: 8328169 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.7647. Min Act: -0.1700
Data Index: 5583852 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.7647. Min Act: -0.1700
Data Index: 4114697 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.7647. Min Act: -0.1700
Data Index: 576365 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.7647. Min Act: -0.1700
Data Index: 2133597 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.7960. Min Act: -0.1700
Data Index: 4265580 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.7960. Min Act: -0.1700
Data Index: 1555329 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.7335. Min Act: -0.1700
Data Index: 4138365 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0460. Min Range: -5.0460
Max Act: 4.7335. Min Act: -0.1700
Data Index: 4572479 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19